Ancient23/MultiAgent-Claude
Setup Prompts for creating a multi agent development environment for Claude Code, using sub agents, commands, and a memory system. Sub agents are research focused and always plan, leaving the main implementation to the parent agent.
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
Copy this rig
# review before running: this installs third-party code $ claude mcp add playwright -- npx @playwright/mcp@latest $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem $ claude mcp add github -- npx -y @modelcontextprotocol/server-github $ claude mcp add memory -- npx -y @modelcontextprotocol/server-memory $ claude mcp add everything -- npx -y @modelcontextprotocol/server-everything $ claude mcp add context7 -- npx -y @upstash/context7-mcp $ npx degit Ancient23/MultiAgent-Claude/.claude ./rig-multiagent-claude # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add playwright -- npx @playwright/mcp@latest $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem $ claude mcp add github -- npx -y @modelcontextprotocol/server-github $ claude mcp add memory -- npx -y @modelcontextprotocol/server-memory $ claude mcp add everything -- npx -y @modelcontextprotocol/server-everything $ claude mcp add context7 -- npx -y @upstash/context7-mcp
$ curl -fsSL --create-dirs -o .claude/agents/agent-factory.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/agent-factory.md $ curl -fsSL --create-dirs -o .claude/agents/bundler-optimization-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/bundler-optimization-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/cli-test-engineer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/cli-test-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/cli-web-bridge-architect.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/cli-web-bridge-architect.md $ curl -fsSL --create-dirs -o .claude/agents/codex-configuration-expert.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/codex-configuration-expert.md $ curl -fsSL --create-dirs -o .claude/agents/context-bundler-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/context-bundler-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-bridge-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/documentation-bridge-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/documentation-sync-guardian.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/documentation-sync-guardian.md $ curl -fsSL --create-dirs -o .claude/agents/electron-app-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/electron-app-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/implementation-verifier.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/implementation-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/memory-unification-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/memory-unification-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/meta-development-orchestrator.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/meta-development-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/openai-bridge-architect.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/openai-bridge-architect.md $ curl -fsSL --create-dirs -o .claude/agents/playwright-test-engineer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/playwright-test-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/playwright-visual-developer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/playwright-visual-developer.md $ curl -fsSL --create-dirs -o .claude/agents/prompt-compression-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/prompt-compression-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/prompt-engineer-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/prompt-engineer-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/react-ui-architect.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/react-ui-architect.md $ curl -fsSL --create-dirs -o .claude/agents/role-instruction-engineer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/role-instruction-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/sync-orchestrator.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/sync-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/template-evolution-tracker.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/template-evolution-tracker.md $ curl -fsSL --create-dirs -o .claude/agents/testing-compatibility-engineer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/testing-compatibility-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/unreal-cpp-api-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/unreal-cpp-api-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/visual-regression-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/visual-regression-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/vue-hybrid-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/vue-hybrid-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/websocket-realtime-engineer.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/websocket-realtime-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-translator.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/workflow-translator.md $ curl -fsSL --create-dirs -o .claude/agents/worktree-coordinator.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/worktree-coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/yaml-schema-specialist.md https://raw.githubusercontent.com/Ancient23/MultiAgent-Claude/main/.claude/agents/yaml-schema-specialist.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (7)
| server | source | est. tokens |
|---|---|---|
| Playwright MCP · "playwright" | npm | 7.5k |
| Sequential Thinking · "sequential-thinking" | npm | 900 |
| Filesystem | npm | 4.2k |
| GitHub MCP · "github" | npm | 18.0k |
| Memory (knowledge graph) · "memory" | npm | 2.6k |
| @modelcontextprotocol/server-everything · "everything" | npm | 2.5k |
| Context7 | npm | 1.2k |
Subagents (29)
| agent-factory model: sonnet | Use this agent PROACTIVELY when you need to create new agents following established patterns, generate agent templates, or design agent specifications. Use PROACTIVELY when user mentions agent creatio |
| bundler-optimization-specialist model: sonnet | Use this agent PROACTIVELY when optimizing build tools and bundle sizes. Use PROACTIVELY when user mentions Webpack, Vite, Rollup, code splitting, tree shaking, bundle analysis, or build performance. |
| cli-test-engineer model: sonnet | Use this agent PROACTIVELY when you need to create comprehensive tests for CLI applications, test command workflows, or validate CLI functionality. Use PROACTIVELY when user mentions CLI testing, comm |
| cli-web-bridge-architect model: sonnet | Use this agent PROACTIVELY when building bridges between CLI tools and web interfaces. Use PROACTIVELY when user mentions CLI-web integration, configuration sharing, process communication, or unified |
| codex-configuration-expert model: sonnet | Use this agent PROACTIVELY when setting up OpenAI Codex, optimizing AGENTS.md files, or configuring repository-level AI guidance. Use PROACTIVELY when user mentions Codex setup, AGENTS.md optimization |
| context-bundler-specialist model: sonnet | Use this agent PROACTIVELY when creating file bundles, optimizing uploads, or managing context for ChatGPT Projects. Use PROACTIVELY when user mentions bundling, file packaging, ChatGPT uploads, proje |
| documentation-bridge-specialist model: sonnet | Use this agent PROACTIVELY when creating multi-platform documentation, user guides, or training materials for cross-platform usage. Use PROACTIVELY when user mentions documentation bridging, platform |
| documentation-sync-guardian model: sonnet | Use this agent PROACTIVELY when you need to keep documentation synchronized with code changes, validate documentation accuracy, or ensure consistency across all project documentation. Use PROACTIVELY |
| electron-app-specialist model: sonnet | Use this agent PROACTIVELY when building desktop applications with Electron. Use PROACTIVELY when user mentions desktop apps, native menus, system tray, auto-updates, or cross-platform distribution. T |
| implementation-verifier model: opus | Verify implementation matches requirements and plans |
| memory-unification-specialist model: sonnet | Use this agent PROACTIVELY when designing shared memory systems, knowledge base integration, or cross-platform persistence. Use PROACTIVELY when user mentions unified memory, shared knowledge, ADRs, p |
| meta-development-orchestrator model: opus | Orchestrates the self-improvement and evolution of the MultiAgent-Claude framework by coordinating specialized agents to analyze framework gaps, generate improvements, test changes, and maintain docum |
| openai-bridge-architect model: sonnet | Use this agent PROACTIVELY when designing cross-platform AI assistant integration, configuration translation, or compatibility layers. Use PROACTIVELY when user mentions OpenAI, ChatGPT, Codex, AGENTS |
| playwright-test-engineer model: sonnet | Use this agent when you need to create, plan, or design Playwright tests for CI pipelines, including E2E testing, visual regression testing, interaction testing, or accessibility testing. This agent s |
| playwright-visual-developer model: sonnet | Implements pixel-perfect UI using Playwright MCP for design iteration. For CI-focused test planning and automation, choose the `playwright-test-engineer` agent instead. |
| prompt-compression-specialist model: sonnet | Use this agent PROACTIVELY when optimizing text for token limits, compressing instructions, or fitting content into character constraints. Use PROACTIVELY when user mentions compression, <redacted>, 1 |
| prompt-engineer-specialist model: sonnet | Use this agent PROACTIVELY when you need to create, review, or improve agent prompts and templates. Use PROACTIVELY when user mentions agent templates, prompt engineering, YAML headers, agent examples |
| react-ui-architect model: sonnet | Use this agent PROACTIVELY when building React applications and component libraries. Use PROACTIVELY when user mentions React hooks, component architecture, state management, React patterns, or UI com |
| role-instruction-engineer model: sonnet | Use this agent PROACTIVELY when creating ChatGPT custom instructions, role-based prompts, or behavior simulation patterns. Use PROACTIVELY when user mentions custom instructions, "act as" prompts, Cha |
| sync-orchestrator model: sonnet | Use this agent PROACTIVELY when designing bidirectional synchronization, managing cross-platform consistency, or resolving conflicts. Use PROACTIVELY when user mentions sync, synchronization, merge co |
| template-evolution-tracker model: sonnet | Use this agent PROACTIVELY when you need to track changes to templates over time, analyze template evolution patterns, or document template modification decisions. Use PROACTIVELY when user mentions t |
| testing-compatibility-engineer model: sonnet | Use this agent PROACTIVELY when designing cross-platform testing strategies, validation frameworks, or test synchronization. Use PROACTIVELY when user mentions compatibility testing, cross-platform QA |
| unreal-cpp-api-specialist model: sonnet | Use this agent PROACTIVELY when developing Unreal Engine 5.5 C++ gameplay systems, implementing GAS (Gameplay Ability System), creating multiplayer features, or optimizing game performance. Use PROACT |
| visual-regression-specialist model: sonnet | Use this agent PROACTIVELY when implementing visual regression testing systems. Use PROACTIVELY when user mentions screenshot testing, visual diffs, pixel comparison, baseline management, or UI consis |
| vue-hybrid-specialist model: sonnet | Use this agent PROACTIVELY when building Vue.js applications with terminal integration. Use PROACTIVELY when user mentions Vue 3, Composition API, terminal-web hybrid interfaces, or Vue with CLI tools |
| websocket-realtime-engineer model: sonnet | Use this agent PROACTIVELY when implementing real-time communication features. Use PROACTIVELY when user mentions WebSockets, Socket.io, real-time sync, live updates, push notifications, or bidirectio |
| workflow-translator model: sonnet | Use this agent PROACTIVELY when converting workflows between platforms, translating process patterns, or mapping execution sequences. Use PROACTIVELY when user mentions workflow conversion, process tr |
| worktree-coordinator model: sonnet | Use this agent PROACTIVELY when managing parallel development with git worktrees. Use PROACTIVELY when user mentions worktrees, parallel branches, concurrent development, or feature isolation. This ag |
| yaml-schema-specialist model: sonnet | Use this agent PROACTIVELY when designing YAML-based configuration systems, component schemas, or template architectures. Use PROACTIVELY when user mentions YAML schemas, variable interpolation, compo |
Slash commands (6)
/generate-agent/generate-role/implement/sync-docs/test-cli/validate-templates
Similar rigs
cassler/awesome-claude-code-setup
Give Claude the super powers it deserves with this power user collection of bash scripts and slash commands
Pragmatist 31.8k tok ·
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
MCP Hoarder 60.2k tok ·
imMamdouhaboammar/agent-kernel
Local governance, memory, failure lessons, and architecture guardrails for Claude Code, Codex, Cursor, Gemini CLI, and other AI coding agents.
MCP Hoarder 34.4k tok ·
nandhasuhendra/dotfiles
My configuration files that I use on several applications and Linux desktops.
MCP Hoarder 19.1k tok ·